Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code structure and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.49
     a
    0.47
    ;
    0.44
    .
    0.43
    ,
    0.43
    -
    0.40
    ),
    0.38
     adenine
    0.37
    )
    0.37
    é
    0.36
    POSITIVE LOGITS
     atualizar
    0.47
    setupUi
    0.46
     സമയ
    0.45
     కార్యక్ర
    0.45
     காவல்துற
    0.44
    取り組み
    0.44
    setWindowTitle
    0.44
     stampa
    0.44
    irmeye
    0.44
     workflow
    0.43
    Act Density 0.036%

    No Known Activations